wassname b3539e50e7 no-cheat check: held-out hacked_E is <=1.1% FP, not ==0; correct caption ...

Re-counted E-by-mode on job-104 A5 route2 rollouts: held-out hacked_E fires
2/1337 file_marker, 0/1386 sentinel, 17/1540 stdout_marker (<=1.1%, detector
cross-mode false positives). The 'hacked_E==0' claim was the smaller harvest;
at n>=1337 the FP floor shows. Claim corrected to '>=98.9% labels withheld'.
Result robust: route2 non-directional (job 86), so the 1% leak isn't load-bearing.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-05 03:01:20 +00:00

..

.gitignore

Merge branch 'probe/distill-cosine' of https://github.com/wassname/projected_grpo into probe/distill-cosine

2026-06-02 07:21:49 +00:00

main.tex

no-cheat check: held-out hacked_E is <=1.1% FP, not ==0; correct caption

2026-06-05 03:01:20 +00:00

nips15submit_e.sty

docs(writeup): NeurIPS-workshop paper skeleton + tectonic compile recipe

2026-06-02 06:59:15 +00:00

refs.bib

paper: framed code blocks, real AntiPaSTO cite, leave-one-out ablation

2026-06-03 11:22:22 +00:00